INDEX

Explanations

words related to religious freedom and religious institutions

oai_token-act-pair · gpt-3.5-turbo

terms related to religious freedom and rights

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ĸļ

-0.79

motion

-0.78

 Incredible

-0.69

 newsp

-0.65

hyde

-0.65

 Toll

-0.62

neau

-0.61

catch

-0.61

vous

-0.61

vious

-0.61

POSITIVE LOGITS

 denominations

0.91

 nuns

0.85

 denomination

0.85

 Judaism

0.84

Jews

0.81

 holiest

0.80

 sect

0.80

 sects

0.79

 choir

0.78

 theology

0.78

Activations Density 0.419%

words related to religious freedom and religious institutions

terms related to religious freedom and rights

No Comments

No Known Activations